Skills
96,981 packaged capabilities and playbooks for agents. Install any of them with one command.
Development
Distributed traces, spans, service dependencies, and request flow analysis. Use when investigating span-level details, failures, performance bottlenecks, or trace correlation. Trigger: "trace analysis", "slow requests", "failed spans", "service dependencies", "distributed trace", "span details", "HTTP status codes in traces", "database query spans", "messaging spans", "gRPC calls", "Lambda cold starts", "trace ID lookup", "exception analysis", "correlate logs and traces", "request attributes". Do NOT use for explaining existing queries, product documentation or configuration questions, service-level RED metrics (use dt-obs-services), log searching (use dt-obs-logs), or problem analysis (use dt-obs-problems).
MUST USE for C#/.NET deterministic tests that require the smallest production seam for DateTime/Task.Delay/File/Environment/Guid/Random, static API preservation, nested/parallel overrides, or no real I/O. USE ONLY when the target workspace contains C# source plus a .csproj or .sln. DO NOT USE for audits, bulk migration, code that already has an injectable seam, or an explicit migration to a user-named existing abstraction (migrate-static-to-wrapper). Use instead of general test generation when the requested test is impossible without a production edit and seam selection is still open.
Service performance monitoring with RED metrics (Rate, Errors, Duration) and runtime-specific telemetry for Java, .NET, Node.js, Python, PHP, and Go. Use when analyzing service health, SLA compliance, or runtime issues. Trigger: "service response time", "error rate", "throughput", "SLA compliance", "service mesh overhead", "JVM GC", "Java heap", "Node.js event loop", ".NET CLR", "Python threads", "PHP OPcache", "Go goroutines", "service performance", "p95 latency", "request failures", "database response time by name". Do NOT use for explaining existing queries, product documentation questions, infrastructure metrics (use dt-obs-hosts), log analysis (use dt-obs-logs), or distributed tracing workflows (use dt-obs-tracing).
Delegate a coding task to Oh My Pi (`omp`) as a background implementer, then review its diff and land it yourself. Use this whenever the user wants to delegate implementation work to Oh My Pi / omp - phrasings like "have omp implement X", "delegate this to oh my pi", "run it through omp", "use oh-my-pi to implement/fix/refactor" - or wants to run a queue of coding tasks through omp while staying the reviewer. DO NOT USE for tasks small enough to do inline, when the user wants the code written directly without delegating, or when they mean the original Pi CLI (`pi`) — that is pi-delegate.
Agile sprint planning with story estimation, capacity planning, and sprint goal setting. Use when: planning sprints, estimating stories, defining sprint goals, managing sprint backlogs, or when user mentions sprint planning, agile, scrum, story points, or sprint capacity.
Plan-then-execute implementation against SPEC.md. Native single-thread loop, no sub-agents. On test or build failure, auto-invokes the backprop skill before retrying — a failed verification always considers whether a new §V invariant would prevent recurrence. Triggers when the user asks to build, implement, execute the spec, or tackle a specific §T task (`build §T.3`, `build --next`, `implement next task`, `run the build`). Expects SPEC.md to exist; if not, defers to the spec skill.
Pick the right Lightning Base Component (`lightning-*`) for a given UI task, retrieve its full API (props, methods, events, slots) from the bundled per-component reference, and wire it into an LWC (LWC `.html`, `.js`, and `.css` files) without breaking SLDS. Use this skill when users say "I need a Lightning modal / datatable / combobox / record form", ask which `lightning-*` component fits a use case, want a shortlist of LBC candidates, are about to hand-roll a UI that a base component already provides, or are editing an LWC bundle's `.html` / `.js` / `.css` and need to select or wire a base component. Also triggers on "Lightning base component", "LBC", "lightning-combobox", "lightning-datatable", "use `lightning-` tag". DO NOT TRIGGER for applying SLDS design tokens, blueprints, or styling guidance in general — that is `design-systems-slds-apply`; this skill only selects and wires `lightning-*` base components.
Implements keyboard, directional, and scene-level focus behavior across SwiftUI and UIKit. Use when managing @FocusState, defaultFocus, focused values, focusable interactions, focus sections, tvOS geometric focus and Siri Remote navigation, watchOS Digital Crown input, visionOS connected-device focus versus gaze hover/input targets, macOS key view loop and Full Keyboard Access, focus restoration after presentation changes, custom focus routing with UIFocusGuide, or debugging focus with UIFocusDebugger
This skill should be used when the user asks to "create an MCP App", "add a UI to an MCP tool", "build an interactive MCP View", "scaffold an MCP App", or needs guidance on MCP Apps SDK patterns, UI-resource registration, MCP App lifecycle, or host integration. Provides comprehensive guidance for building MCP Apps with interactive UIs.
Manage unified memory and thermals during long-running ML jobs on NVIDIA DGX Spark. Use when planning memory headroom for a training run on GB10, when a job OOMs on unified memory, or when monitoring temperature and power during multi-hour training.
Full Sentry SDK setup for Cloudflare Workers and Pages. Use when asked to "add Sentry to Cloudflare Workers", "install @sentry/cloudflare", or configure error monitoring, tracing, logging, crons, or AI monitoring for Cloudflare Workers, Pages, Durable Objects, Queues, Workflows, or Hono on Cloudflare.
Set up a working ML training/inference environment on NVIDIA DGX Spark (GB10, aarch64, CUDA 13). Use when installing PyTorch/Unsloth/TRL/vLLM on DGX Spark, hitting libcudart or wheel-ABI errors on aarch64, or choosing between NGC containers and bare pip installs.
MUST READ before writing or modifying ADK agent code. ADK API quick reference for Python — agent types, tool definitions, orchestration patterns, callbacks, and state management. Includes an index of all ADK documentation pages. Do NOT use for creating new projects (use adk-scaffold).
Create, amend, or backprop bugs into SPEC.md at repo root. Sole mutator of the project spec. Triggers when the user asks to write a spec, start a new spec, distill a spec from existing code, add invariants, amend sections (§G, §C, §I, §V, §T, §B), or record a bug via backprop. Common phrasings: "write the spec for...", "new spec", "bug: ...", "amend §V.3", "distill spec from code", "spec this idea". Reads and follows FORMAT.md for the caveman encoding rules and pipe-table shape of §T and §B
GitHub CLI operations via `gh` command. Use when working with GitHub repositories, pull requests, issues, code search, releases, or any GitHub API operation. This skill replaces the GitHub MCP server with direct CLI calls. Triggers on: GitHub, PR, pull request, issue, repo, branch, release, tag, commit, fork, merge, review, gh.
This skill should be used when setting up, auditing, or enforcing internationalization/localization in UI codebases (React/TS, i18next or similar, JSON locales), including installing/configuring the i18n framework, replacing hard-coded strings, ensuring en-US/zh-CN coverage, mapping error codes to localized messages, and validating key parity, pluralization, and formatting.
Run a structured discovery session to build an Allium specification through conversation. Use when the user wants to create a new spec from scratch, elicit or gather requirements, capture domain behaviour, specify a feature or system, define what a system should do, or is describing functionality and needs help shaping it into a specification.
Creates, modifies, or manages Salesforce Experience Cloud LWR sites via DigitalExperience metadata. Always trigger when the tasks involve LWR sites configurations, e.g. creating/modifying pages/routes/views/theme layouts/branding sets, previewing sites, or creating/modifying guest sharing rule (metadata type sharingGuestRules)/guest user access/sharing records to guest users, or when user provides a guest user ID (15 or 18 characters starting with 005). NEVER trigger for React or any other ui bundle framework. LWR sites ONLY.
You are an expert in Nest.js with deep knowledge of enterprise-grade Node.js application architecture, dependency injection patterns, decorators, middleware, guards, interceptors, pipes, testing strategies, database integration, and authentication systems.
The basics of how to program GPUs using Mojo. Use this skill in addition to mojo-syntax when writing Mojo code that targets GPUs or other accelerators. Use targeting code to NVIDIA, AMD, Apple silicon GPUs, or others. Use this skill to overcome misconceptions about how Mojo GPU code is written.
State machine-based vector animation with runtime interactivity and web integration. Use this skill when creating interactive animations, state-driven UI, animated components with logic, or designer-created animations with runtime control. Triggers on tasks involving Rive, state machines, interactive vector animations, animation with input handling, ViewModel data binding, or React Rive integration. Alternative to Lottie for animations requiring state machines and two-way interactivity
Use when adding Auth0 authentication to any app and unsure which SDK or skill to use. Detects the project's framework and routes to the right setup workflow — use this as the entry point even if the user just says "add login to my app" or "set up Auth0" without naming a framework
Set up ADR governance, audit architecture and drift, or plan and execute bounded refactors and code simplification. Use when work needs binding architecture decisions, library reuse, shared-code ownership, provider-to-local mapping, or architecture PR review.
This skill should be used when the user asks to "build a scroll animation", "add ScrollTrigger", "pin a section while scrolling", "scrub an animation to scroll", "create a hero timeline", "do a horizontal scroll section", "split text and animate words", "animate a layout change with GSAP Flip", "sync ScrollTrigger with Lenis", "Lenis smooth scroll jittery", "ScrollTrigger markers drift", "ScrollTrigger pins break with Lenis/Locomotive", or "set up smooth scroll with GSAP pinning". Covers GSAP timelines, ScrollTrigger, SplitText, Flip, and Lenis/Locomotive smooth-scroll sync for code-driven web motion.
Diagnose what state one open PR is actually in — unfinished plan steps, missing review, unresolved conversations, red CI, base conflicts, missing QA evidence, merge-ready — then run the matching chain of om-* skills in order and publish a status report. Use for "finish PR 123", "what is left on PR 123", "drive PR 123 to the end".
Frida 17 JavaScript API compatibility checker and fixer. Use when writing, reviewing, or fixing Frida scripts, especially when migrating from older Frida versions. Detects deprecated APIs removed in Frida 17 (May 2025) and provides correct replacements. Covers Module, Memory, Process APIs and common naming conflicts.
Set up Tailwind v4 with shadcn/ui using the @theme inline pattern and CSS variable architecture. Four-step pattern: CSS variables, Tailwind mapping, base styles, automatic dark mode. Prevents 8 documented errors. Use when initializing React projects with Tailwind v4, or fixing colors not working, tw-animate-css errors, @theme inline dark mode conflicts, @apply breaking, v3 migration issues
React DevTools CLI for AI agents. Use when the user asks you to debug a React or React Native app at runtime, inspect component props/state/hooks, diagnose render performance, profile re-renders, find slow components, or understand why something re-renders. Triggers include "why does this re-render", "inspect the component", "what props does X have", "profile the app", "find slow components", "debug the UI", "check component state", "the app feels slow", or any React runtime debugging task.
Handles files in Convex: upload URLs, storing blobs from actions, serving with getUrl or an HTTP action, metadata from the _storage table, and deletion. Use when users upload images or documents, when an action fetches a file from a third party, or when a file URL expires unexpectedly.
Adversarial senior-engineer review for agent-generated plans, designs, and architectures. Treats the current output as junior work, constructs a senior reviewer whose domain expertise comes from live codebase research plus web research of current best practices, diagnoses altitude failures (too vague or too granular), then rewrites the plan into a scoped, state-of-the-art version. Use when the user says "junior to senior", "senior review", "review this like a staff engineer", when a plan feels hand-wavy or lost in details, or before committing to any agent-written plan.
Extract an Allium specification from an existing codebase. Use when the user has existing code and wants to distil behaviour into a spec, reverse engineer a specification from implementation, generate a spec from code, turn implementation into a behavioural specification, or document what a codebase does in Allium terms
Use when a Lightning Web Component data need is described in ambiguous natural language — turn "get contact info" or "show account data" into a clear, PRD-ready data-requirements spec. TRIGGER when the user says "define data requirements for this LWC", "turn this PRD data section into validated object/field names", "recommend GraphQL vs UIAPI for this data need", "validate these Salesforce API names", or "spec out the LDS adapter for this component", or references LWC bundle files (`.js`, `.js-meta.xml`) whose data layer is not yet specified. DO NOT TRIGGER when the data layer is already fully specified, when authoring the actual query or adapter code from a known spec, or when implementing an LWC end-to-end (use experience-lwc-generate).
Turn ambiguous coding requests into verified Cursor Agent implementation specs. Use when the user wants requirements, an implementation plan, or a spec before coding; include source checks, needed ADRs, and agreed delivery. Do not use for already specified direct implementation or memory cleanup.
Tend the Allium garden. Use when the user wants to write, edit, update, add to, improve, clarify, refine, restructure, fix or migrate Allium specs. Covers adding entities, rules, triggers, surfaces and contracts, fixing syntax or validation errors, renaming or refactoring within specs, migrating specs to a new language version, and translating requirements into well-formed specifications. Pushes back on vague requirements.
Turn ambiguous coding requests into verified Codex implementation specs. Use when the user wants requirements, an implementation plan, or a spec before coding; include source checks, needed ADRs, and agreed delivery. Do not use for already specified direct implementation or memory cleanup.
Sofia, the Product Owner: turns any input (an idea, brief, PRD, transcript, notes) into a ticket''s requirements, slices initiatives into epics and epics into stories, writes and refines tickets, runs the board, validates the tree, replans when a change lands, and sets up the ticket store. Use when the user asks for Sofia or the product owner, or says ''create a spec'', ''distill this PRD'', ''write the initiative from'', ''slice this'', ''split this epic'', ''break this into stories'', ''make a ticket'', ''refine this ticket'', ''what''s ready'', ''status of'', ''publish'', ''validate these tickets'', ''this changed, what now'', ''set up the ticket store''.
Security guidelines for writing secure code. Use when writing code, reviewing code for vulnerabilities, or asking about secure coding practices like 'check for SQL injection' or 'review security'. IMPORTANT: Always consult this skill when writing or reviewing any code that handles user input, authentication, file operations, database queries, network requests, cryptography, or infrastructure configuration (Terraform, Kubernetes, Docker, GitHub Actions) — even if the user doesn't explicitly mention security. Also use when users ask to 'review my code', 'check this for bugs', or 'is this safe'.
Official integration patterns for Mapbox GL JS across popular web frameworks (React, Vue, Svelte, Angular). Covers setup, lifecycle management, token handling, search integration, and common pitfalls. Based on Mapbox's create-web-app scaffolding tool.
Extend Pydantic AI agents with capabilities from pydantic-ai-harness — the Coder coding agent, file and shell tools in local or sandboxed workspaces (Modal, E2B, Sprites, smolvm), Code Mode, sub-agents and planning, memory and skills, context compaction, guardrails and spend limits, web research and browsers, hosted SaaS integrations, step persistence, and background agents on Render Workflows. Use when the user mentions pydantic-ai-harness or pydantic_ai_harness, imports a harness capability such as Coder, CodeMode, FileSystem, Shell, SubAgents, Memory, or ToolGuardrail, or wants a Pydantic AI agent that edits files, runs commands or agent-written Python, delegates, remembers, manages long context, stays within limits, or runs model and tool operations as chained Render task runs.
Weed the Allium garden. Find where Allium specifications and implementation code have diverged, and help resolve the divergences. Use when the user wants to check spec-code alignment, compare specs against implementation, audit for spec drift or violations, sync specs with code or code with specs, or verify whether the implementation matches what the spec says.
Implement feature flags in Next.js or SvelteKit code with the Flags SDK (`flags` npm package). Use when installing or configuring the SDK, declaring flags with `flag()`, wiring a provider adapter (`@flags-sdk/vercel`, Statsig, LaunchDarkly, PostHog, GrowthBook, Global Config, OpenFeature, Split, Flagsmith, Reflag, Optimizely, or custom), using `identify`, `dedupe`, or `evaluate`, keeping pages static with precompute, setting up Flags Explorer and the Vercel Toolbar, or encrypting flag values. Triggers: `flags/next`, `flags/sveltekit`, `flags/react`, `@flags-sdk/*`, `vercelAdapter`, precompute. For planning a flag, for Vercel Flags rollouts, experiments, and the `vercel flags` CLI, or for other frameworks, use the `vercel-flags` skill.
Survey a whole React codebase as a senior React engineer, using React Doctor's scan as evidence, then produce a prioritized audit and self-contained implementation plans for other agents (or cheaper models) to execute. Read-only on source code — it plans improvements, it does not apply them. Use when the user asks to "improve the React code", "audit this codebase", "make this app faster / more robust", or wants a roadmap of fixes rather than a review of a single diff. For a regression check or a fix-it-now pass, use the `react-doctor` skill instead
Optimize what selected Next.js client navigations include before the click under Partial Prefetching. Use after Cache Components and Partial Prefetching are adopted when the user wants selected URL-specific UI to be instant, wants reusable content to wait for navigation, or needs to choose between default, viewport, and intent prefetching. Requires Next.js 16.3+.
Bug → spec protocol. When a bug is found or a test fails, trace the cause, decide whether a new §V invariant would catch recurrence, append to §B. This is the one non-obvious thing SDD does that plan-then-execute doesn't. Triggers on test failure, bug report, post-mortem, or explicit user ask.
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.